© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 12276
    Prev
    Next
    INDEX
    Explanations

    up followed by words like start, town, close

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    が
    -0.98
    があり
    -0.86
    pples
    -0.82
     σαν
    -0.80
    hrens
    -0.79
    余裕
    -0.78
    跎
    -0.74
    lossen
    -0.73
    や
    -0.73
     birthplace
    -0.73
    POSITIVE LOGITS
     Up
    1.01
    為に
    0.96
    Up
    0.85
    lese
    0.82
     Ups
    0.82
    を入力
    0.82
    Funktionen
    0.81
     UP
    0.80
     uplifting
    0.78
     ups
    0.78
    Activations Density 0.017%

    No Known Activations